Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    computation and action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഒറ്റ
    0.42
     डिजाइनर
    0.41
     Jetzt
    0.39
     نہيں
    0.39
     offizi
    0.38
    κής
    0.37
     sekarang
    0.36
    স্ফ
    0.36
    ικά
    0.36
    幟
    0.36
    POSITIVE LOGITS
    Fiber
    0.42
    opting
    0.40
    Spacing
    0.38
    ุปกรณ์
    0.38
     actuator
    0.38
    Cleanup
    0.38
    Servo
    0.37
    sn
    0.37
    imerick
    0.37
    Act
    0.37
    Act Density 0.000%

    No Known Activations